io.py 54.4 KB
Newer Older
(no author)'s avatar
(no author) committed
1
2
3
4
5
6
7
8
9
#!/usr/bin/env python
# encoding: utf-8
"""
I/O routines supporting reading a number of file formats.

Created by rayg Apr 2009.
Copyright (c) 2009 University of Wisconsin SSEC. All rights reserved.
"""

10
import os, logging
11
import numpy
12
from functools import reduce
(no author)'s avatar
   
(no author) committed
13
14

LOG = logging.getLogger(__name__)
(no author)'s avatar
(no author) committed
15

16
17
Loadable_Types = set()

(no author)'s avatar
   
(no author) committed
18
19
20
try:
    import pyhdf
    from pyhdf.SD import SD,SDC, SDS, HDF4Error
21
    Loadable_Types.add("hdf")
(no author)'s avatar
   
(no author) committed
22
23
24
25
26
27
except:
    LOG.info('no pyhdf module available for HDF4')
    pyhdf = None
    SD = SDC = SDS = object
    HDF4Error = EnvironmentError
    
28
29
try:
    import h5py
30
    from h5py import h5d
31
    Loadable_Types.add("h5")
32
except ImportError:
(no author)'s avatar
   
(no author) committed
33
34
    LOG.info('no h5py module available for reading HDF5')
    h5py = None
(no author)'s avatar
(no author) committed
35

36
37
38
# the newer netCDF library that replaced pycdf
try:
    import netCDF4
39
    Loadable_Types.update(["nc", "nc4", "cdf", ])
40
41
42
43
except:
    LOG.info("unable to import netcdf4 library")
    netCDF4 = None

(no author)'s avatar
(no author) committed
44
45
46
try:
    import dmv as dmvlib
    LOG.info('loaded dmv module for AERI data file access')
47
    Loadable_Types.update(["cxs", "rnc", "cxv", "csv", "spc", "sum", "uvs", "aeri", ])
(no author)'s avatar
(no author) committed
48
49
50
51
except ImportError:
    LOG.info('no AERI dmv data file format module')
    dmvlib = None

(no author)'s avatar
   
(no author) committed
52
53
54
try:
    import adl_blob
    LOG.info('adl_blob module found for JPSS ADL data file access')
55
    # TODO, what is the loadable file extension?
(no author)'s avatar
   
(no author) committed
56
57
58
59
except ImportError:
    LOG.info('no adl_blob format handler available')
    adl_blob = None

60
61
62
try :
    from osgeo import gdal
    LOG.info('loading osgeo module for GeoTIFF data file access')
63
    Loadable_Types.update(["tiff", "tif", "tifa", ])
64
65
66
67
except :
    LOG.info('no osgeo available for reading GeoTIFF data files')
    gdal = None

68
UNITS_CONSTANT = "units"
(no author)'s avatar
(no author) committed
69

70
71
72
fillValConst1 = '_FillValue'
fillValConst2 = 'missing_value'

73
74
75
76
ADD_OFFSET_STR   = 'add_offset'
SCALE_FACTOR_STR = 'scale_factor'
SCALE_METHOD_STR = 'scaling_method'

77
78
79
UNSIGNED_ATTR_STR = "_unsigned"

SIGNED_TO_UNSIGNED_DTYPES = {
80
81
82
83
                                numpy.dtype(numpy.int8):    numpy.dtype(numpy.uint8),
                                numpy.dtype(numpy.int16):   numpy.dtype(numpy.uint16),
                                numpy.dtype(numpy.int32):   numpy.dtype(numpy.uint32),
                                numpy.dtype(numpy.int64):   numpy.dtype(numpy.uint64),
84
85
                            }

86
87
88
89
90
91
92
93
94
95
96
class IOUnimplimentedError(Exception):
    """
    The exception raised when a requested io operation is not yet available.
    
        msg  -- explanation of the problem
    """
    def __init__(self, msg):
        self.msg = msg
    def __str__(self):
        return self.msg

97
98
99
100
101
102
class IONonnumericalTypeError(Exception):
    """
    A type was encountered that numpy doesn't know how to deal with - e.g. netCDF variable-length string arrays
    """
    pass

103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
class CaseInsensitiveAttributeCache (object) :
    """
    A cache of attributes for a single file and all of it's variables.
    This cache is considered uncased, it will store all attributes it caches
    in lower case and will lower case any strings it is asked to search for
    in the cache.
    When variable or global attribute sets are not yet loaded and something
    from that part of the file is requested the cache will transparently load
    attributes from the file behind the scenes and build the cache for that
    part of the file.
    """
    
    def __init__(self, fileObject) :
        """
        set up the empty cache and hang on to the file object we'll be caching
        """
        
        self.fileToCache             = fileObject
        self.globalAttributesLower   = None
        self.variableAttributesLower = { }
    
    def _load_global_attributes_if_needed (self) :
        """
        load up the global attributes if they need to be cached
        """
        
        # load the attributes from the file if they aren't cached
        if self.globalAttributesLower is None :
            LOG.debug ("Loading file global attributes into case-insensitive cache.")
            tempAttrs                  = self.fileToCache.get_global_attributes(caseInsensitive=False)
            self.globalAttributesLower = dict((k.lower(), v) for k, v in tempAttrs.items())
    
    def _load_variable_attributes_if_needed (self, variableName) :
        """
        load up the variable attributes if they need to be cached
        """
        
        # make a lower cased version of the variable name
        tempVariableName = variableName.lower()
        
        # load the variable's attributes from the file if they aren't cached
Eva Schiffer's avatar
Eva Schiffer committed
144
        if tempVariableName not in self.variableAttributesLower :
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
            LOG.debug ("Loading attributes for variable \"" + variableName + "\" into case-insensitive cache.")
            tempAttrs = self.fileToCache.get_variable_attributes(variableName, caseInsensitive=False)
            # now if there are any attributes, make a case insensitive version
            self.variableAttributesLower[tempVariableName] = dict((k.lower(), v) for k, v in tempAttrs.items())
    
    def get_variable_attribute (self, variableName, attributeName) :
        """
        get the specified attribute for the specified variable,
        if this variable's attributes have not yet been loaded
        they will be loaded and cached
        """
        
        self._load_variable_attributes_if_needed(variableName)
        
        toReturn = None
        tempVariableName  =  variableName.lower()
        tempAttributeName = attributeName.lower()
        if (tempVariableName in self.variableAttributesLower) and (tempAttributeName in self.variableAttributesLower[tempVariableName]) :
            toReturn = self.variableAttributesLower[tempVariableName][tempAttributeName]
        else:
            LOG.debug ("Attribute \"" + attributeName + "\" was not present for variable \"" + variableName + "\".")
        
        return toReturn
    
    def get_variable_attributes (self, variableName) :
        """
        get the variable attributes for the variable name given
        """
        
        self._load_variable_attributes_if_needed(variableName)
        
        toReturn = self.variableAttributesLower[variableName.lower()] if (variableName.lower() in self.variableAttributesLower) else None
        
        return toReturn
    
    def get_global_attribute (self, attributeName) :
        """
        get a global attribute with the given name
        """
        
        self._load_global_attributes_if_needed()
        
        toReturn = self.globalAttributesLower[attributeName.lower()] if (attributeName.lower() in self.globalAttributesLower) else None
        
        return toReturn
    
    def get_global_attributes (self) :
        """
        get the global attributes,
        """
        
        self._load_global_attributes_if_needed()
        
        toReturn = self.globalAttributesLower
        
        return toReturn
201
202
203
204
205
206
207
208
    
    def is_loadable_type (self, name) :
        """
        check to see if the indicated variable is a type that can be loaded
        """
        
        # TODO, are there any bad types for these files?
        return True
209

210
211
212
213
214
215
216
217
218
219
220
221
222
def _get_data_uptype (input_dtype) :
    """
    Given an input data type, figure out what type we need to upcast it to.

    Note: Glance expects all it's data to get upcast into floats for the purposes of it's
    later math manipulations.
    """

    default_uptype = numpy.float32
    default_finfo  = numpy.finfo(default_uptype)
    input_info     = numpy.finfo(input_dtype) if  numpy.issubdtype(input_dtype, numpy.floating,) else numpy.iinfo(input_dtype)

    # if our input won't fit into the default, pick a bigger type
223
    if (default_finfo.min > input_info.min) or (default_finfo.max < input_info.max) :
224
225
226
227
228
229
230
        LOG.debug("Input data will not fit in default float32 data type, using larger type.")
        default_uptype = numpy.float64

    # FUTURE, if we reach a point where a float64 isn't big enough, this will need to be revisited

    return default_uptype

231
class hdf (object):
(no author)'s avatar
(no author) committed
232
233
234
235
236
    """wrapper for HDF4 dataset for comparison
    __call__ yields sequence of variable names
    __getitem__ returns individual variables ready for slicing to numpy arrays
    """
    
237
238
    _hdf = None
    
239
    def __init__(self, filename, allowWrite=False):
240
        
(no author)'s avatar
   
(no author) committed
241
242
243
        if pyhdf is None:
            LOG.error('pyhdf is not installed and is needed in order to read hdf4 files')
            assert(pyhdf is not None)
244
245
246
        mode = SDC.READ
        if allowWrite:
            mode = mode | SDC.WRITE
247
248
249
        
        self._hdf = SD(filename, mode)
        self.attributeCache = CaseInsensitiveAttributeCache(self)
(no author)'s avatar
(no author) committed
250
251

    def __call__(self):
252
253
254
        """
        yield names of variables to be compared
        """
Eva Schiffer's avatar
Eva Schiffer committed
255
        return list(self._hdf.datasets())
(no author)'s avatar
(no author) committed
256
    
257
258
259
260
    # this returns a numpy array with a copy of the full, scaled
    # data for this variable, if the data type must be changed to allow
    # for scaling it will be (so the return type may not reflect the
    # type found in the original file)
(no author)'s avatar
(no author) committed
261
    def __getitem__(self, name):
262
263
264
        # defaults
        scale_factor = 1.0
        add_offset = 0.0
265
        data_type = None 
(no author)'s avatar
(no author) committed
266
        scaling_method = None
267
268
269
270
271
272
273
274
275
        
        # get the variable object and use it to
        # get our raw data and scaling info
        variable_object = self.get_variable_object(name)
        raw_data_copy = variable_object[:]
        try :
            # TODO, this currently won't work with geocat data, work around it for now
            scale_factor, scale_factor_error, add_offset, add_offset_error, data_type = SDS.getcal(variable_object)
        except HDF4Error:
276
277
            # load just the scale factor and add offset information by hand
            temp = self.attributeCache.get_variable_attributes(name)
Eva Schiffer's avatar
Eva Schiffer committed
278
            if ADD_OFFSET_STR in temp :
279
                add_offset = temp[ADD_OFFSET_STR]
280
                data_type = numpy.dtype(type(add_offset))
Eva Schiffer's avatar
Eva Schiffer committed
281
            if SCALE_FACTOR_STR in temp :
282
                scale_factor = temp[SCALE_FACTOR_STR]
283
                data_type = numpy.dtype(type(scale_factor))
Eva Schiffer's avatar
Eva Schiffer committed
284
            if SCALE_METHOD_STR in temp :
285
                scaling_method = temp[SCALE_METHOD_STR]
286
        SDS.endaccess(variable_object)
(no author)'s avatar
(no author) committed
287
        
288
289
290
291
        # don't do lots of work if we don't need to scale things
        if (scale_factor == 1.0) and (add_offset == 0.0) :
            return raw_data_copy
        
292
293
294
295
296
297
298
299
        # at the moment geocat has several scaling methods that don't match the normal standards for hdf
        """
        please see constant.f90 for a more up to date version of this information:
            INTEGER(kind=int1) :: NO_SCALE              ! 0
            INTEGER(kind=int1) :: LINEAR_SCALE          ! 1
            INTEGER(kind=int1) :: LOG_SCALE             ! 2
            INTEGER(kind=int1) :: SQRT_SCALE            ! 3 
        """
300
        if scaling_method == 0 :
301
            return raw_data_copy
302
        if not ((scaling_method is None) or (int(scaling_method) <= 1)) :
303
304
            LOG.warning ('Scaling method of \"' + str(scaling_method) + '\" will be ignored in favor of hdf standard method. '
                         + 'This may cause problems with data consistency')
305
        
306
307
308
        # if we don't have a data type something strange has gone wrong
        assert(not (data_type is None))
        
309
310
        # get information about where the data is the missing value
        missing_val = self.missing_value(name)
311
        missing_mask = numpy.zeros(raw_data_copy.shape, dtype=numpy.bool)
312
313
        if missing_val is not None :
            missing_mask[raw_data_copy == missing_val] = True
314
        
315
        # create the scaled version of the data
316
        scaled_data_copy                = numpy.array(raw_data_copy, dtype=data_type)
317
        scaled_data_copy[~missing_mask] = (scaled_data_copy[~missing_mask] * scale_factor) + add_offset #TODO, type truncation issues?
318
319
320
321
        
        return scaled_data_copy 
    
    def get_variable_object(self, name):
322
        return self._hdf.select(name)
323
    
(no author)'s avatar
(no author) committed
324
    def missing_value(self, name):
325
        
326
        return self.get_attribute(name, fillValConst1)
327
328
329
330
331
332
333
334
335
    
    def create_new_variable(self, variablename, missingvalue=None, data=None, variabletocopyattributesfrom=None):
        """
        create a new variable with the given name
        optionally set the missing value (fill value) and data to those given
        
        the created variable will be returned, or None if a variable could not
        be created
        """
(no author)'s avatar
(no author) committed
336
        
337
        raise IOUnimplimentedError('Unable to create variable in hdf file, this functionality is not yet available.')
338
        
339
        #return None
340
341
342
343
344
345
    
    def add_attribute_data_to_variable(self, variableName, newAttributeName, newAttributeValue) :
        """
        if the attribute exists for the given variable, set it to the new value
        if the attribute does not exist for the given variable, create it and set it to the new value
        """
346
347
        
        raise IOUnimplimentedError('Unable add attribute to hdf file, this functionality is not yet available.')
348
        
349
        #return
350
    
351
    def get_variable_attributes (self, variableName, caseInsensitive=True) :
352
353
354
355
        """
        returns all the attributes associated with a variable name
        """
        
356
        #toReturn = None
357
358
359
360
361
362
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attributes(variableName)
        else :
            toReturn = self.get_variable_object(variableName).attributes()
        
        return toReturn
363
    
364
    def get_attribute(self, variableName, attributeName, caseInsensitive=True) :
365
366
367
368
369
        """
        returns the value of the attribute if it is available for this variable, or None
        """
        toReturn = None
        
370
371
372
373
374
375
376
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attribute(variableName, attributeName)
        else :
            temp_attributes = self.get_variable_attributes(variableName, caseInsensitive=False)
            
            if attributeName in temp_attributes :
                toReturn = temp_attributes[attributeName]
377
378
        
        return toReturn
(no author)'s avatar
(no author) committed
379
    
380
381
382
383
384
    def get_global_attributes(self, caseInsensitive=True) :
        """
        get a list of all the global attributes for this file or None
        """
        
385
        #toReturn = None
386
387
        
        if caseInsensitive :
388
            toReturn = self.attributeCache.get_global_attributes()
389
390
391
392
393
394
        else :
            toReturn = self._hdf.attributes()
        
        return toReturn
    
    def get_global_attribute(self, attributeName, caseInsensitive=True) :
(no author)'s avatar
(no author) committed
395
396
397
398
399
400
        """
        returns the value of a global attribute if it is available or None
        """
        
        toReturn = None
        
401
402
403
404
405
        if caseInsensitive :
            toReturn = self.attributeCache.get_global_attribute(attributeName)
        else :
            if attributeName in self._hdf.attributes() :
                toReturn = self._hdf.attributes()[attributeName]
(no author)'s avatar
(no author) committed
406
407
        
        return toReturn
408
409
410
411
412
413
414
415
    
    def is_loadable_type (self, name) :
        """
        check to see if the indicated variable is a type that can be loaded
        """
        
        # TODO, are there any bad types for these files?
        return True
(no author)'s avatar
(no author) committed
416

417
class nc (object):
418
    """wrapper for netcdf4-python data access for comparison
(no author)'s avatar
(no author) committed
419
420
421
422
    __call__ yields sequence of variable names
    __getitem__ returns individual variables ready for slicing to numpy arrays
    """
    
423
    _nc = None
424
425
426
427
    _var_map = None

    # walk down through all groups and get variable names and objects
    def _walkgroups(self, start_at, prefix=None, ):
428
        # look through the variables that are here
Eva Schiffer's avatar
Eva Schiffer committed
429
        for var_name in start_at.variables:
430
431
            temp_name = var_name if prefix is None or len(prefix) <= 0 else prefix + "/" + var_name
            yield temp_name, start_at[var_name]
432
        # look through the groups that are here
Eva Schiffer's avatar
Eva Schiffer committed
433
        for group_name in start_at.groups:
434
435
436
            grp_str = group_name if prefix is None or len(prefix) <= 0 else prefix + "/" + group_name
            for more_var_name, more_var_obj in self._walkgroups(start_at.groups[group_name], prefix=grp_str):
                yield more_var_name, more_var_obj
437
    
438
439
    def __init__(self, filename, allowWrite=False):
        
440
441
442
        if netCDF4 is None:
            LOG.error('netCDF4 is not installed and is needed in order to read NetCDF files')
            assert(netCDF4 is not None)
(no author)'s avatar
   
(no author) committed
443
        
444
        mode = 'r'
445
        if allowWrite :
446
447
            mode = 'a' # a is for append, if I use w it creates a whole new file, deleting the old one

448
        self._nc = netCDF4.Dataset(filename, mode)
449
        self.attributeCache = CaseInsensitiveAttributeCache(self)
450
451
452
        self._var_map = { }
        for var_name, var_obj in self._walkgroups(self._nc,) :
            self._var_map[var_name] = var_obj
453

(no author)'s avatar
(no author) committed
454
    def __call__(self):
455
456
457
458
        """
        yield names of variables in this file
        """

Eva Schiffer's avatar
Eva Schiffer committed
459
        return list(self._var_map)
460

(no author)'s avatar
(no author) committed
461
    def __getitem__(self, name):
462
463
464
465
466
467
468
        """
        this returns a numpy array with a copy of the full, scaled
        data for this variable, if the data type must be changed to allow
        for scaling it will be (so the return type may not reflect the
        type found in the original file)
        """

469
470
        LOG.debug("loading variable data for: " + name)

471
472
473
        # get the variable object and use it to
        # get our raw data and scaling info
        variable_object = self.get_variable_object(name)
474

475
476
        # get our data, save the dtype, and make sure it's a more flexible dtype for now
        variable_object.set_auto_maskandscale(False)  # for now just do the darn calculations ourselves
477
478
        temp_input_data = variable_object[:]
        LOG.debug("Native input dtype: " + str(temp_input_data.dtype))
479
480
        # if this is object data, stop because we can't run our regular analysis on that kind
        if temp_input_data.dtype == object :
481
482
            LOG.warning("Variable '" + name + "' has a data type of 'object'. This type of data cannot be analyzed by Glance. "
                        "This variable will not be analyzed.")
483
484
485
486
487
488
489
490
            raise IONonnumericalTypeError("Variable '" + name + "' is of data type 'object'. "
                                          "This program can't analyze non-numerical data.")
        """
            Note to self, if we ever do want to access data in a numpy array with dtype=object, for some
            reason this library is packing that into a a zero dimensional tuple or something similar.
            I was able to unpack the data using a construction like: temp_input_data = temp_input_data[()]
            After that the array can be indexed into as normal for a numpy array.
        """
491
492
493
        dtype_to_use = _get_data_uptype(temp_input_data.dtype)
        LOG.debug("Choosing dtype " + str(dtype_to_use) + " for our internal representation of this data.")
        scaled_data_copy = numpy.array(temp_input_data, dtype=dtype_to_use,)
494
495

        # get the attribute cache so we can check on loading related attributes
496
        temp = self.attributeCache.get_variable_attributes(name)
497
498
499

        # get information about where the data is the missing value
        missing_val = self.missing_value(name)
500
        missing_mask = numpy.zeros(scaled_data_copy.shape, dtype=numpy.bool)
501
502
        if missing_val is not None:
            missing_mask[scaled_data_copy == missing_val] = True
503
504
505
506

        #***** just do the darn unsigned handling ourselves, ugh

        # if our data is labeled as being unsigned by the appropriately set attribute
507
        if UNSIGNED_ATTR_STR in temp and str(temp[UNSIGNED_ATTR_STR]).lower() == "true":
508
509
            LOG.debug("Correcting for unsigned values in variable data.")
            where_temp = (scaled_data_copy < 0.0) & ~missing_mask # where we have negative but not missing data
510
            scaled_data_copy[where_temp] += (numpy.iinfo(numpy.uint16).max + 1.0) # add the 2's complement
511
512
513
514
515
516
517
518
519

        #***** end of handling the unsigned attribute

        ###### the start of the scaling code
        # Note, I had to turn this back on because the netcdf4 library is behaving erratically when unsigned is set

        # get the scale factor and add offset from the attributes
        scale_factor = 1.0
        add_offset = 0.0
Eva Schiffer's avatar
Eva Schiffer committed
520
        if SCALE_FACTOR_STR in temp :
521
            scale_factor = temp[SCALE_FACTOR_STR]
Eva Schiffer's avatar
Eva Schiffer committed
522
        if ADD_OFFSET_STR in temp :
523
            add_offset = temp[ADD_OFFSET_STR]
524

525
526
        # don't do work if we don't need to unpack things
        if (scale_factor != 1.0) or (add_offset != 0.0) :
527

528
            LOG.debug("Manually applying scale (" + str(scale_factor) + ") and add offset (" + str(add_offset) + ").")
529

530
531
532
533
534
535
536
            # unpack the data
            scaled_data_copy[~missing_mask] = (scaled_data_copy[~missing_mask] * scale_factor) + add_offset

        ###### end of the scaling code

        """
        #TODO, this section was for when we had to do the unsigned correction after unpacking
Eva Schiffer's avatar
Eva Schiffer committed
537
        if UNSIGNED_ATTR_STR in temp and str(temp[UNSIGNED_ATTR_STR]).lower() == ( "true" ) :
538
539
540
541
542
543
544

            LOG.debug("fixing unsigned values in variable " + name)

            # load the scale factor and add offset
            scale_factor = 1.0
            add_offset = 0.0
            temp = self.attributeCache.get_variable_attributes(name)
Eva Schiffer's avatar
Eva Schiffer committed
545
            if SCALE_FACTOR_STR in temp :
546
                scale_factor = temp[SCALE_FACTOR_STR]
Eva Schiffer's avatar
Eva Schiffer committed
547
            if ADD_OFFSET_STR in temp :
548
549
550
551
                add_offset = temp[ADD_OFFSET_STR]

            # get the missing value and figure out the dtype of the original data
            missing_val  = self.missing_value(name)
552
            orig_dtype   = numpy.array([missing_val,]).dtype
Eva Schiffer's avatar
Eva Schiffer committed
553
            needed_dtype = SIGNED_TO_UNSIGNED_DTYPES[orig_dtype] if orig_dtype in SIGNED_TO_UNSIGNED_DTYPES else None
554
555
556

            if needed_dtype is not None :
                # now figure out where all the corrupted values are, and shift them up to be positive
557
                needs_fix_mask = (scaled_data_copy < add_offset) & (scaled_data_copy != missing_val)
558
                # we are adding the 2's complement, but first we're scaling it appropriately
559
                scaled_data_copy[needs_fix_mask] += ((numpy.iinfo(numpy.uint16).max + 1.0) * scale_factor)
560
        """
561

562
        return scaled_data_copy
563
    
564
565
566
567
    # TODO, this hasn't been supported in other file types
    def close (self) :
        self._nc.close()
        self._nc = None
568
        self._var_map = None
569

570
    def get_variable_object(self, name):
571

572
        return self._var_map[name]
573
    
(no author)'s avatar
(no author) committed
574
    def missing_value(self, name):
575
        
576
577
578
579
580
581
582
583
584
585
586
        toReturn = None
        
        temp = self.attributeCache.get_variable_attribute(name, fillValConst1)
        if temp is not None :
            toReturn = temp
        else :
            temp = self.attributeCache.get_variable_attribute(name, fillValConst2)
            if temp is not None :
                toReturn = temp
        
        return toReturn
587

588
589
590
591
592
593
594
595
    def create_new_variable(self, variablename, missingvalue=None, data=None, variabletocopyattributesfrom=None):
        """
        create a new variable with the given name
        optionally set the missing value (fill value) and data to those given
        
        the created variable will be returned, or None if a variable could not
        be created
        """
596
597

        # TODO, this will not work with groups
598
        #self._nc.nc_redef() # TODO?
599
600
        
        # if the variable already exists, stop with a warning
Eva Schiffer's avatar
Eva Schiffer committed
601
        if variablename in self._nc.variables :
602
603
            LOG.warning("New variable name requested (" + variablename + ") is already present in file. " +
                        "Skipping generation of new variable.")
604
            return None
605
606
        # if we have no data we won't be able to determine the data type to create the variable
        if (data is None) or (len(data) <= 0) :
607
608
            LOG.warning("Data type for new variable (" + variablename + ") could not be determined. " +
                        "Skipping generation of new variable.")
609
            return None
Eva Schiffer's avatar
Eva Schiffer committed
610

611
        # TODO, the type managment here is going to cause problems with larger floats, review this
612
        #dataType = None
613
614
        if numpy.issubdtype(data.dtype, int) :
            dataType = numpy.int
615
616
            #print("Picked INT")
        # TODO, at the moment the fill type is forcing me to use a double, when sometimes I want a float
617
618
        #elif numpy.issubdtype(data.dtype, numpy.float32) :
        #    dataType = numpy.float
619
        #    print("Picked FLOAT")
620
621
        elif numpy.issubdtype(data.dtype, float) :
            dataType = numpy.float64
622
623
            #print("Picked DOUBLE")
        # what do we do if it's some other type?
624
625
        else :
            dataType = data.dtype
626
627
628
629
630
        
        # create and set all the dimensions
        dimensions = [ ]
        dimensionNum = 0
        for dimSize in data.shape :
631
632
633
            tempName = variablename + '-index' + str(dimensionNum)
            self._nc.createDimension(tempName, dimSize)
            dimensions.append(tempName)
634
635
636
            dimensionNum = dimensionNum + 1
        
        # create the new variable
637
638
639
        #print('variable name: ' + variablename)
        #print('data type:     ' + str(dataType))
        #print('dimensions:    ' + str(dimensions))
640
        # if a missing value was given, use that
641
642
643
644
        if missingvalue is None :
            newVariable = self._nc.createVariable(variablename, dataType, tuple(dimensions))
        else :
            newVariable = self._nc.createVariable(variablename, dataType, tuple(dimensions), fill_value=missingvalue, )
645
646
647
        
        # if we have a variable to copy attributes from, do so
        if variabletocopyattributesfrom is not None :
648
649
            attributes = self.get_variable_attributes(variabletocopyattributesfrom, caseInsensitive=False)

Eva Schiffer's avatar
Eva Schiffer committed
650
            for attribute in attributes :
651
652
                if attribute.lower() != "_fillvalue" :
                    setattr(newVariable, attribute, attributes[attribute])
653

654
        #self._nc.nc_enddef() # TODO?
655

656
657
        # if data was given, use that
        if data is not None :
658
659

            newVariable[:] = data
660

661
        return newVariable
662

663
    def add_attribute_data_to_variable(self, variableName, newAttributeName, newAttributeValue, variableObject=None,) :
664
665
666
667
        """
        if the attribute exists for the given variable, set it to the new value
        if the attribute does not exist for the given variable, create it and set it to the new value
        """
668
669
        # TODO, this will not work with groups

670
671
        if variableObject is None :
            variableObject = self.get_variable_object(variableName)
672
        
673
        #self._nc.nc_redef() # TODO?
674
675
676

        setattr(variableObject, newAttributeName, newAttributeValue)

677
        #self._nc.nc_enddef() # TODO?
678

679
680
681
        # TODO, this will cause our attribute cache to be wrong!
        # TODO, for now, brute force clear the cache
        self.attributeCache = CaseInsensitiveAttributeCache(self)
682
683
        
        return
684
    
685
    def get_variable_attributes (self, variableName, caseInsensitive=True) :
686
687
688
689
        """
        returns all the attributes associated with a variable name
        """
        
690
        #toReturn = None
691
692
693
694
        
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attributes(variableName)
        else :
695
696
697
698
699
            toReturn = { }
            tempVarObj   = self.get_variable_object(variableName)
            tempAttrKeys = tempVarObj.ncattrs()
            for attrKey in tempAttrKeys :
                toReturn[attrKey] = getattr(tempVarObj, attrKey)
700
701
        
        return toReturn
702
    
703
    def get_attribute(self, variableName, attributeName, caseInsensitive=True) :
704
705
706
707
708
        """
        returns the value of the attribute if it is available for this variable, or None
        """
        toReturn = None
        
709
710
711
712
713
714
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attribute(variableName, attributeName)
        else :
            temp_attributes = self.get_variable_attributes(variableName, caseInsensitive=False)
            
            if attributeName in temp_attributes :
715
                toReturn = getattr(self.get_variable_object, attributeName)
716
717
718
719
720
721
722
723
        
        return toReturn
    
    def get_global_attributes(self, caseInsensitive=True) :
        """
        get a list of all the global attributes for this file or None
        """
        
724
        #toReturn = None
725
        
726
        if caseInsensitive :
727
            toReturn = self.attributeCache.get_global_attributes()
728
        else :
729
730
731
732
            toReturn = { }
            tempAttrKeys = self._nc.ncattrs()
            for attrKey in tempAttrKeys :
                toReturn[attrKey] = getattr(self._nc, attrKey)
733

734
        return toReturn
735
    
736
    def get_global_attribute(self, attributeName, caseInsensitive=True) :
737
738
739
740
741
742
        """
        returns the value of a global attribute if it is available or None
        """
        
        toReturn = None
        
743
744
745
        if caseInsensitive :
            toReturn = self.attributeCache.get_global_attribute(attributeName)
        else :
746
            if attributeName in self._nc.ncattrs() :
747
                toReturn = getattr(self._nc, attributeName)
748
749
        
        return toReturn
750
751
752
753
754
    
    def is_loadable_type (self, name) :
        """
        check to see if the indicated variable is a type that can be loaded
        """
755
756

        return True
757

(no author)'s avatar
(no author) committed
758
759
760
nc4 = nc
cdf = nc

761
762
# TODO remove
#FIXME_IDPS = [ '/All_Data/CrIS-SDR_All/ES' + ri + band for ri in ['Real','Imaginary'] for band in ['LW','MW','SW'] ] 
763

(no author)'s avatar
(no author) committed
764
class h5(object):
765
766
767
768
    """wrapper for HDF5 datasets
    """
    _h5 = None
    
769
    def __init__(self, filename, allowWrite=False):
770
771
        self.attributeCache = CaseInsensitiveAttributeCache(self)
        
772
773
774
        mode = 'r'
        if allowWrite :
            mode = 'r+'
(no author)'s avatar
   
(no author) committed
775
776
777
        if h5py is None:
            LOG.error('h5py module is not installed and is needed in order to read h5 files')
            assert(h5py is not None)
778
        self._h5 = h5py.File(filename, mode)
779
780
    
    def __call__(self):
781
782
783
784
        
        variableList = [ ]
        def testFn (name, obj) :
            #print ('checking name: ' + name)
785
            #print ('object: ' + str(obj))
786
787
788
789
            
            if isinstance(obj, h5py.Dataset) :
                try :
                    tempType = obj.dtype # this is required to provoke a type error for closed data sets
790
                    
791
                    #LOG.debug ('type: ' + str(tempType))
792
793
794
795
796
797
798
799
800
                    variableList.append(name)
                except TypeError :
                    LOG.debug('TypeError prevents the use of variable ' + name
                              + '. This variable will be ignored')
        
        self._h5.visititems(testFn)
        
        LOG.debug('variables from visiting h5 file structure: ' + str(variableList))
        
801
        return variableList
802
803
804
805
806
    
    @staticmethod
    def trav(h5,pth): 
        return reduce( lambda x,a: x[a] if a else x, pth.split('/'), h5)
        
807
808
809
810
811
    # this returns a numpy array with a copy of the full, scaled
    # data for this variable, if the data type must be changed to allow
    # for scaling it will be (so the return type may not reflect the
    # type found in the original file)
    def __getitem__(self, name):
812
        
813
814
815
816
817
818
819
820
        # defaults
        scale_factor = 1.0
        add_offset = 0.0
        
        # get the variable object and use it to
        # get our raw data and scaling info
        variable_object = self.get_variable_object(name)
        raw_data_copy = variable_object[:]
821
822
823
824

        # pick a data type to use internally
        data_type = _get_data_uptype(raw_data_copy.dtype)

825
826
827
828
        #print ('*************************')
        #print (dir (variable_object.id)) # TODO, is there a way to get the scale and offset through this?
        #print ('*************************')
        
829
        # load the scale factor and add offset
830
        temp = self.attributeCache.get_variable_attributes(name)
Eva Schiffer's avatar
Eva Schiffer committed
831
        if SCALE_FACTOR_STR in temp :
832
            scale_factor = temp[SCALE_FACTOR_STR]
Eva Schiffer's avatar
Eva Schiffer committed
833
        if ADD_OFFSET_STR in temp :
834
            add_offset = temp[ADD_OFFSET_STR]
835
836
837
838
839
840
        # todo, does cdf have an equivalent of endaccess to close the variable?
        
        # don't do lots of work if we don't need to scale things
        if (scale_factor == 1.0) and (add_offset == 0.0) :
            return raw_data_copy
        
841
842
        # get information about where the data is the missing value
        missing_val = self.missing_value(name)
843
        missing_mask = numpy.zeros(raw_data_copy.shape, dtype=numpy.bool)
844
845
        if missing_val is not None:
            missing_mask[raw_data_copy == missing_val] = True
846
        
847
        # create the scaled version of the data
848
        scaled_data_copy = numpy.array(raw_data_copy, dtype=data_type)
849
        scaled_data_copy[~missing_mask] = (scaled_data_copy[~missing_mask] * scale_factor) + add_offset #TODO, type truncation issues?
850
851
852
853
        
        return scaled_data_copy
    
    def get_variable_object(self,name):
854
855
856
        return h5.trav(self._h5, name)
    
    def missing_value(self, name):
857
858
859
860
861
862
863
        
        toReturn = None
        
        # get the missing value if it has been set
        variableObject = self.get_variable_object(name)
        pListObj = variableObject.id.get_create_plist()
        fillValueStatus = pListObj.fill_value_defined()
Eva Schiffer's avatar
Eva Schiffer committed
864
        if (h5d.FILL_VALUE_DEFAULT == fillValueStatus) or (h5d.FILL_VALUE_USER_DEFINED == fillValueStatus) :
865
            temp = numpy.array((1), dtype=variableObject.dtype)
866
867
868
869
            pListObj.get_fill_value(temp)
            toReturn = temp
        
        return toReturn
870
871
872
873
874
875
876
877
878
    
    def create_new_variable(self, variablename, missingvalue=None, data=None, variabletocopyattributesfrom=None):
        """
        create a new variable with the given name
        optionally set the missing value (fill value) and data to those given
        
        the created variable will be returned, or None if a variable could not
        be created
        """
879
        
880
        raise IOUnimplimentedError('Unable to create variable in hdf 5 file, this functionality is not yet available.')
881
        
882
        #return None
883
884
885
886
887
888
    
    def add_attribute_data_to_variable(self, variableName, newAttributeName, newAttributeValue) :
        """
        if the attribute exists for the given variable, set it to the new value
        if the attribute does not exist for the given variable, create it and set it to the new value
        """
889
890
        
        raise IOUnimplimentedError('Unable to add attribute to hdf 5 file, this functionality is not yet available.')
891
        
892
        #return
893
    
894
    def get_variable_attributes (self, variableName, caseInsensitive=True) :
895
896
897
898
        """
        returns all the attributes associated with a variable name
        """
        
899
        #toReturn = None
900
901
902
903
904
905
906
        
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attributes(variableName)
        else :
            toReturn = self.get_variable_object(variableName).attrs
        
        return toReturn
907
    
908
    def get_attribute(self, variableName, attributeName, caseInsensitive=True) :
909
910
911
912
913
        """
        returns the value of the attribute if it is available for this variable, or None
        """
        toReturn = None
        
914
915
916
917
918
        if caseInsensitive :
            toReturn = self.attributeCache.get_variable_attribute(variableName, attributeName)
        else :
            temp_attrs = self.get_variable_attributes(variableName, caseInsensitive=False)
            
919
            if attributeName in temp_attrs :
920
921
922
923
924
925
926
927
928
                toReturn = temp_attrs[attributeName]
        
        return toReturn
    
    def get_global_attributes(self, caseInsensitive=True) :
        """
        get a list of all the global attributes for this file or None
        """
        
929
        #toReturn = None
930
        
931
        if caseInsensitive :
932
            toReturn = self.attributeCache.get_global_attributes()
933
934
        else :
            toReturn = self._h5.attrs
935
936
        
        return toReturn
(no author)'s avatar
(no author) committed
937
    
938
    def get_global_attribute(self, attributeName, caseInsensitive=True) :
(no author)'s avatar
(no author) committed
939
940
941
942
943
944
        """
        returns the value of a global attribute if it is available or None
        """
        
        toReturn = None
        
945
946
947
948
949
        if caseInsensitive :
            toReturn = self.attributeCache.get_global_attribute(attributeName)
        else :
            if attributeName in self._h5.attrs :
                toReturn = self._h5.attrs[attributeName]
(no author)'s avatar
(no author) committed
950
951
        
        return toReturn
952
953
954
955
956
957
958
959
    
    def is_loadable_type (self, name) :
        """
        check to see if the indicated variable is a type that can be loaded
        """
        
        # TODO, are there any bad types for these files?
        return True
(no author)'s avatar
(no author) committed
960

(no author)'s avatar
(no author) committed
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996

class aeri(object):
    """wrapper for AERI RNC/SUM/CXS/etc datasets
    """
    _dmv = None
    _vectors = { }
    _scalars = { }
    
    @staticmethod
    def _meta_mapping(fp):
        ids = fp.metaIDs()
        names = [fp.queryMetaDescString(1, id_, fp.SHORTNAME) for id_ in ids]
        assert len(ids) == len(names)
        return (dict((n, i) for n, i in zip(names, ids)))
    
    def _inventory(self):
        fp = self._dmv
        assert(fp is not None)
        # get list of vectors and scalars
        self._vectors = dict( (fp.queryVectorDescString(n,fp.SHORTNAME), n) for n in fp.vectorIDs() )
        self._scalars = self._meta_mapping(fp)

    def __init__(self, filename, allowWrite=False):
        assert(allowWrite==False)
        if dmvlib is None:
            LOG.error('cannot open AERI files without dmv module being available')
            return
        self._dmv = dmvlib.dmv()
        rc = self._dmv.openFile(filename)
        if rc!=0:
            LOG.error("unable to open file, rc=%d" % rc)
            self._dmv = None        
        else:
            self._inventory()
    
    def __call__(self):
Eva Schiffer's avatar
Eva Schiffer committed
997
        return list(self._vectors) + list(self._scalars)
(no author)'s avatar
(no author) committed
998
999
1000
        
    def __getitem__(self, name):
        fp = self._dmv
For faster browsing, not all history is shown. View entire blame